Setup ruff and format

pyproject.toml

@@ -38,6 +38,7 @@ dev = [
   "pytest>=7.0.0",
   "pytest-cov>=4.0.0",
   "mypy>=1.0.0",
+  "ruff>=0.8.0",
 ]
 docs = [
   "sphinx>=8.0.0; python_version >= '3.10'",
@@ -80,3 +81,32 @@ exclude_lines = [
 markers = [
   "slow: marks tests as slow (deselect with '-m \"not slow\"')",
 ]
+
+[tool.ruff]
+target-version = "py38"
+line-length = 88
+
+[tool.ruff.lint]
+select = [
+  "E",   # pycodestyle errors
+  "W",   # pycodestyle warnings
+  "F",   # pyflakes
+  "I",   # isort
+  "UP",  # pyupgrade
+  "B",   # flake8-bugbear
+  "RUF", # ruff-specific rules
+  "NPY", # numpy-specific rules
+  "C4",  # flake8-comprehensions
+]
+ignore = [
+  "E501",    # line length handled by ruff format
+  "RUF001",  # ambiguous unicode in strings (intentional math symbols: γ, ξ)
+  "RUF002",  # ambiguous unicode in docstrings
+]
+
+[tool.ruff.lint.per-file-ignores]
+"src/tailestim/estimators/plot/*" = ["F841", "E741"]
+"tests/*" = ["NPY002"]
+
+[tool.ruff.lint.isort]
+known-first-party = ["tailestim"]

src/tailestim/__init__.py

@@ -3,23 +3,21 @@
 # SPDX-License-Identifier: MIT
 
 from .datasets import TailData
-
 from .estimators.base import BaseTailEstimator
+from .estimators.estimator_set import TailEstimatorSet
 from .estimators.hill import HillEstimator
-from .estimators.moments import MomentsEstimator
 from .estimators.kernel import KernelTypeEstimator
+from .estimators.moments import MomentsEstimator
 from .estimators.pickands import PickandsEstimator
 from .estimators.smooth_hill import SmoothHillEstimator
 
-from .estimators.estimator_set import TailEstimatorSet
-
 __all__ = [
-    'TailData',
-    'BaseTailEstimator',
-    'HillEstimator',
-    'MomentsEstimator',
-    'KernelTypeEstimator',
-    'PickandsEstimator',
-    'SmoothHillEstimator',
-    'TailEstimatorSet',
-]
+    "BaseTailEstimator",
+    "HillEstimator",
+    "KernelTypeEstimator",
+    "MomentsEstimator",
+    "PickandsEstimator",
+    "SmoothHillEstimator",
+    "TailData",
+    "TailEstimatorSet",
+]

src/tailestim/datasets.py

@@ -1,13 +1,15 @@
+import logging
 import os
+
 import numpy as np
-import logging
+
 
 class TailData:
     """Load and manage tail distribution datasets.
-    
+
     This class provides functionality to load datasets either from the package's
     built-in data directory using a name, or from a custom path provided by the user.
-    
+
     Parameters
     ----------
     name : str, optional
@@ -16,7 +18,7 @@ class TailData:
     path : str, optional
         Path to a custom dataset file. If provided, this takes precedence over `name`.
         Must be provided if `name` is None.
-        
+
     Attributes
     ----------
     name : str or None
@@ -25,39 +27,39 @@ class TailData:
         Path to the dataset file if a custom dataset was loaded.
     data : numpy.ndarray
         The loaded dataset as a numpy array.
-        
+
     Examples
     --------
     Load a built-in dataset:
-    
+
     >>> data = TailData(name='CAIDA_KONECT')
     >>> print(len(data.data))
-    
+
     Load a custom dataset:
-    
+
     >>> data = TailData(path='path/to/my/data.dat')
     >>> print(len(data.data))
     """
-    
+
     def __init__(self, name=None, path=None):
         if name is None and path is None:
             raise ValueError("Either 'name' or 'path' must be provided")
-        
+
         if name is not None and path is not None:
             logging.info("Both 'name' and 'path' provided; 'path' will take precedence")
-        
+
         self.name = name
         self.path = path
         self.data = self.load_data()
 
     def load_data(self):
         """Load data from either a built-in dataset or a custom file path.
-        
+
         Returns
         -------
         numpy.ndarray
             The loaded dataset as a numpy array.
-            
+
         Raises
         ------
         FileNotFoundError
@@ -70,20 +72,22 @@ def load_data(self):
             logging.info(f"Using custom path: {file_path}")
         else:
             # Use the package data directory with the provided name
-            data_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'data')
-            file_path = os.path.join(data_dir, f'{self.name}.dat')
+            data_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "data")
+            file_path = os.path.join(data_dir, f"{self.name}.dat")
             logging.info(f"Using package data path: {file_path}")
 
         # Check if the file exists
         if not os.path.exists(file_path):
             if self.path is not None:
                 raise FileNotFoundError(f"Data file not found at path: {file_path}")
             else:
-                raise FileNotFoundError(f"Data file '{self.name}.dat' not found in package data directory.")
+                raise FileNotFoundError(
+                    f"Data file '{self.name}.dat' not found in package data directory."
+                )
 
         # Load the data from the file using the provided method
         logging.info(f"Loading data from file: {file_path}")
-        with open(file_path, 'r') as file:
+        with open(file_path) as file:
             lines = file.readlines()
 
         # Determine the total number of data points
@@ -94,14 +98,14 @@ def load_data(self):
         # Populate the ordered_data array
         for line in lines:
             degree, count = line.strip().split()
-            ordered_data[current_index:current_index + int(count)] = float(degree)
+            ordered_data[current_index : current_index + int(count)] = float(degree)
             current_index += int(count)
 
         return ordered_data
 
     def __repr__(self):
         """Return a string representation of the TailData object.
-        
+
         Returns
         -------
         str
@@ -110,4 +114,4 @@ def __repr__(self):
         if self.path is not None:
             return f"TailData(path='{self.path}', data_length={len(self.data)})"
         else:
-            return f"TailData(name='{self.name}', data_length={len(self.data)})"
+            return f"TailData(name='{self.name}', data_length={len(self.data)})"

src/tailestim/estimators/__init__.py

@@ -1,19 +1,19 @@
 """Estimators for tail index estimation."""
 
 from .base import BaseTailEstimator
+from .estimator_set import TailEstimatorSet
 from .hill import HillEstimator
-from .moments import MomentsEstimator
 from .kernel import KernelTypeEstimator
+from .moments import MomentsEstimator
 from .pickands import PickandsEstimator
 from .smooth_hill import SmoothHillEstimator
-from .estimator_set import TailEstimatorSet
 
 __all__ = [
-    'BaseTailEstimator',
-    'HillEstimator',
-    'MomentsEstimator',
-    'KernelTypeEstimator',
-    'PickandsEstimator',
-    'SmoothHillEstimator',
-    'TailEstimatorSet',
+    "BaseTailEstimator",
+    "HillEstimator",
+    "KernelTypeEstimator",
+    "MomentsEstimator",
+    "PickandsEstimator",
+    "SmoothHillEstimator",
+    "TailEstimatorSet",
 ]

src/tailestim/estimators/base.py

@@ -1,10 +1,14 @@
 """Base class for tail index estimation."""
-import numpy as np
+
 from abc import ABC, abstractmethod
-from typing import Dict, Any, Tuple, Union
-from numpy.random import BitGenerator, SeedSequence, RandomState, Generator
+from typing import Any, Dict, Tuple, Union
+
+import numpy as np
+from numpy.random import BitGenerator, Generator, RandomState, SeedSequence
+
 from .result import TailEstimatorResult
 
+
 class BaseTailEstimator(ABC):
     """Abstract base class for tail index estimation.
 
@@ -22,12 +26,15 @@ class BaseTailEstimator(ABC):
     **kwargs : dict
         Additional parameters specific to each estimation method.
     """
-    
+
     def __init__(
-            self,
-            bootstrap: bool = True,
-            base_seed: Union[None, SeedSequence, BitGenerator, Generator, RandomState] = None,
-            **kwargs):
+        self,
+        bootstrap: bool = True,
+        base_seed: Union[
+            None, SeedSequence, BitGenerator, Generator, RandomState
+        ] = None,
+        **kwargs,
+    ):
         self.bootstrap = bootstrap
         self.base_seed = base_seed
         self.kwargs = kwargs
@@ -36,12 +43,12 @@ def __init__(
     @abstractmethod
     def _estimate(self, ordered_data: np.ndarray) -> Tuple:
         """Core estimation method to be implemented by each specific estimator.
-        
+
         Parameters
         ----------
         ordered_data : np.ndarray
             Data array in decreasing order.
-            
+
         Returns
         -------
         Tuple
@@ -51,34 +58,32 @@ def _estimate(self, ordered_data: np.ndarray) -> Tuple:
 
     def fit(self, data: np.ndarray) -> None:
         """Fit the estimator to the data.
-        
+
         Parameters
         ----------
         data : np.ndarray
             Input data array (e.g., degree sequence). The data will automatically be sorted in decreasing order.
         """
-        ordered_data = np.sort(data)[::-1]  # Each estimating functions require the data to be in decreasing order
+        ordered_data = np.sort(data)[
+            ::-1
+        ]  # Each estimating functions require the data to be in decreasing order
         self.results = self._estimate(ordered_data)
 
     @abstractmethod
     def get_params(self) -> Dict[str, Any]:
         """Get the parameters of the estimator.
-        
+
         Returns
         -------
         dict
             Dictionary containing the parameters of the estimator.
         """
-        return {
-            "bootstrap": self.bootstrap,
-            "base_seed": self.base_seed,
-            **self.kwargs
-        }
+        return {"bootstrap": self.bootstrap, "base_seed": self.base_seed, **self.kwargs}
 
     @abstractmethod
     def get_result(self) -> TailEstimatorResult:
         """Get the estimated parameters.
-        
+
         Returns
         -------
         TailEstimatorResult
@@ -96,7 +101,7 @@ def get_result(self) -> TailEstimatorResult:
         if self.results is None:
             raise ValueError("Model not fitted yet. Call fit() first.")
         return TailEstimatorResult()
-    
+
     def __repr__(self) -> str:
         """Return a string representation of the estimator."""
         return f"{self.__class__.__name__}(bootstrap={self.bootstrap}, base_seed={self.base_seed}, kwargs={self.kwargs})"
@@ -108,19 +113,19 @@ def __str__(self) -> str:
         estim_str += f"Estimator Type: {self.__class__.__name__}\n"
         estim_str += "-" * 50 + "\n"
         estim_str += f"Fitted: {'Yes' if self.results is not None else 'No'}\n"
-        
+
         # Add the arguments provided
         estim_str += "Arguments:\n"
         estim_str += f"  bootstrap: {self.bootstrap}\n"
         estim_str += f"  base_seed: {self.base_seed}\n"
-        
+
         # Add any additional kwargs
         if self.kwargs:
             for key, value in self.kwargs.items():
                 estim_str += f"  {key}: {value}\n"
-        
-        # If the model is not fitted, return just the estim_str 
+
+        # If the model is not fitted, return just the estim_str
         if self.results is None:
             return estim_str + "Model not fitted yet. Call fit() first."
-        
-        return estim_str 
+
+        return estim_str